laskoviymishka commented on code in PR #809: URL: https://github.com/apache/iceberg-go/pull/809#discussion_r3001994552
########## table/equality_delete_writer.go: ########## @@ -0,0 +1,194 @@ +// Licensed to the Apache Software Foundation (ASF) under one +// or more contributor license agreements. See the NOTICE file +// distributed with this work for additional information +// regarding copyright ownership. The ASF licenses this file +// to you under the Apache License, Version 2.0 (the +// "License"); you may not use this file except in compliance +// with the License. You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, +// software distributed under the License is distributed on an +// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +// KIND, either express or implied. See the License for the +// specific language governing permissions and limitations +// under the License. + +package table + +import ( + "context" + "errors" + "fmt" + "iter" + + "github.com/apache/arrow-go/v18/arrow" + "github.com/apache/iceberg-go" + "github.com/apache/iceberg-go/internal" + iceio "github.com/apache/iceberg-go/io" + "github.com/google/uuid" +) + +// EqualityDeleteSchema projects a table schema to only the fields specified +// by the given field IDs. The resulting schema is suitable for writing +// equality delete files — it contains only the columns that form the +// delete key. +// +// Returns an error if any of the field IDs are not found in the table schema. +func EqualityDeleteSchema(tableSchema *iceberg.Schema, fieldIDs []int) (*iceberg.Schema, error) { + if len(fieldIDs) == 0 { + return nil, errors.New("equality field IDs must not be empty") + } + + fields := make([]iceberg.NestedField, 0, len(fieldIDs)) + for _, id := range fieldIDs { + f, ok := tableSchema.FindFieldByID(id) + if !ok { + return nil, fmt.Errorf("field ID %d not found in table schema", id) + } + + fields = append(fields, f) + } Review Comment: There's Schema.Select, but it works by names not field IDs, and uses PruneColumns which handles nested fields. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
